PMA (version 1.1)

breastdata: Breast cancer gene expression + DNA copy number data set from Chin et al (2006), Cancer Cell

Description

This data set consists of gene expression and DNA copy number measurements on a set of 89 samples. This example is used in Witten, Tibshirani and Hastie (2008).

Usage

data(breastdata)

Format

The format is a list containing the following elements: - dna: a 2149x89 matrix of CGH spots x Samples - rna: a 19672x89 matrix of Genes x Samples - chrom: a 2149-vector of chromosomal location of each CGH spot - nuc: a 2149-vector of nucleotide position for each CGH spot - gene: a 19672-vector wiith an accession number for each gene - genenames: a 19672-vector with a name for each gene - genechr: a 19672-vector with a chromosomal location for each gene - genedesc: a 19672-vector with a description for each gene - genepos: a 19672-vector with a nucleotide position for each gene

Details

This data set can be used to perform integrative analysis of gene expression and DNA copy number data, as in e.g. Witten and Tibshirani and Hastie (2008). That is, we can look for sets of genes that are associated with regions of chromosomal gain/loss.

Missing values were imputed using 5-nearest neighbors (see library pamr).

References

Chin, DeVries, Fridlyand, et al. (2006) Cancer Cell 10, 529-541.

Used as an example in Witten, Tibshirani and Hastie (2008) 'A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis.'

Examples

# NOT RUN {
data(breastdata)
attach(breastdata)
PlotCGH(dna[,1], chrom=chrom, main="Sample 1", nuc=nuc)
detach(breastdata)
# }